This paper introduces a novel distributed decision support system to help radiologists in the diagnosis of soft tissue tumors (STT). Decision support systems are based on pattern recognition engines that discriminate between benign/malignant character and histological groups with a satisfactory estimated efficiency. This system is based on a distributed architecture with three specialized nodes: Radiologist Visual Interface, Information System and Decision Support Web-services. The visual interface is the radiologists and clinicians' point of access to local and remote STT registers, statistical analysis tools and distributed pattern recognition engines. A location-independent and multi-platform system has been developed in order to connect hospitals and institutions to research useful tools in clinical and laboratory environments. The nodes maintenance and upgrade are automatically controlled by the architecture. This tool will be useful regarding the objective methodology to assist radiologist decision in a new case and will help the education of the new radiologists with no expertise in STT.