The potential of Case-Based Reasoning to use the knowledge gained from past experiences to solve problematic situations has made this Artificial Intelligence technique a useful decision support tool in different environmental domains such as wastewater treatment. Case-Based Reasoning tools automatically identify similarities between present and previous situations (cases) and reuse the experiences gained from the previous situations to solve current problems. Case retrieval can be considered to be the most important step in the process of Case-Based Reasoning. In the present study we propose incorporating a relevance network in order to increase the accuracy and the efficiency of case retrieval. The result is a context-sensitive feature-weighting methodology capable of defining the model of relationships between the different attributes or features that define the context in which Case-Based Reasoning is applied. These features affect the retrieval procedure directly. The feature's degree of relevance in the network is easily translated into a set of simple rules and applied during case retrieval, specifically during the similarity calculation. The results obtained in the present study show significant improvements in the accuracy of case retrieval. With the approach presented here experts considered more than 90% of the retrieved cases to be completely relevant according to the knowledge these cases provided for dealing with solids separation problems.