Abstract Database search engines are generally used in a one-shot fashion in which a user provides query information to the system and, in return, the system provides a number of database instances to the user. A relevance feedback system allows the user to indicate to the system which of these instances are desirable, or relevant, and which are not. Based on this feedback, the system modifies its retrieval mechanism in an attempt to return a more desirable instance set to the user. In this paper, we present a relevance feedback technique that uses decision trees to learn a common thread among instances marked relevant. We apply our technique in a preexisting content-based image retrieval (CBIR) system that is used to access high resolution computed tomographic images of the human lung. We compare our approach to a commonly used relevance feedback technique for CBIR, which modifies the weights of a K nearest neighbor retriever. The results show that our approach achieves better retrieval as measured in off-line experiments and as judged by a radiologist who is a lung specialist.