CAD methods may provide radiologists with tools to obtain more accurate diagnoses for lung cancer. Considerable effort has been devoted to developing CAD tools for CXR; however, these are limited by the fundamental constraints of the projective CXR modality. CT provides far more detailed information that can be exploited better by CAD systems. There has been very little work done in this area to date, although the basic technology has already been developed through the more extensive research in the computer vision areas supported by industry and the military. Initial prototype CT CAD systems have been described that are highly effective in detecting small pulmonary nodules and in predicting malignancy of nodules. CT is now achieving momentum in the study of lung cancer. It has taken time for this modality to gain acceptance because of several factors: higher radiation dose, higher cost, and the novelty of use in this application. It is important to note that the technology for CT scanners is still rapidly evolving. As the speed, resolution, and cost of CT scanners continue to improve, computer techniques for the measurement and analysis of nodules will also achieve corresponding improvements in accuracy and diagnostic utility. Future knowledge-based CT CAD systems will provide detailed analysis of the related conditions of the lungs, such as emphysema, and diagnostic analysis of nodules. The issue is not whether CAD will improve the performance and capabilities of the radiologist, but at what rate their development and the corresponding improvement will occur. Current prototype CAD systems may be considered as tools. As such they will improve the performance of the user/radiologist if they are well engineered and if the user understands their capabilities and limitations. These systems need to be improved by knowledge-based engineering, which is notoriously difficult to implement robustly and requires model refinement and optimization based on a large database of cases. Research should be directed at developing these methods rather than comparing prototype systems with current practices. Future performance should be expected to exceed that of today's grand masters.