Abstract. Digital pathology or telepathology intends to extend the usage of electronic images for diagnostical, support or educational purposes in anatomical or clinical pathology. Available approaches have not found wide acceptance in routine pathology, mainly due to the limitations of image retrieval. In this paper we propose a semantic retrieval system for the pathology domain. The system brings both text and image information together and offers advanced content-based retrieval services for diagnosis, differential diagnosis and teaching tasks. The core of the system is a Semantic Web gathering both ontological domain knowledge, and rules describing key tasks and processes in pathology.