The application of scientific methodology to clinical practice is typically realized through recommendations, policies and protocols represented as Clinical Practice Guidelines (CPGs). CPGs have the purpose to help the clinicians in their choices and to improve the patient care process. Currently, there have been considerable efforts in digital CPGs for their application to build Clinical Decision Support Systems (CDSSs) in order to deploy them in several hospitals. The representation of guidelines and their introduction in Clinical Information System (CIS) can lead to efficient Clinical Decision Support Systems (CDSS), however this poses several interesting challenges as it involves problems of knowledge representation, inference, workflow definition, access to unstructured databases of medical records and others. In this paper we describe the architecture of the Guideline Engine, as part of the KON 3 (Knowledge ON ONcology through ONtology) project. We use a semantic web approach - employing a domain ontology, a patient ontology, decision rules and a Guideline Engine formed by a Process Engine and by a Rule Engine. A Guideline Engine is a computer program which can interpret a clinical guideline represented in a computerized format and perform actions towards the user of an electronic health record (EHR). We also report a specific case study of the application of the model in oncology.