The access to relevant, up-to-date and reliable information is a time critical, but nevertheless very important task in the daily work of physicians and nurses. hyperCIS developed an intelligent information retrieval system (IRS) with a knowledge-guided user front-end and an automatic generation of search engine queries. The medical knowledge of MeSH (Medical Subject Headings) classification was transferred into a Topic Map, the new XML-based knowledge representation standard (ISO 13250). A graphical user-interface allows the fast and associative browsing in networks of themes. Each theme or topic, as a node of the topic map, contains information on title, synonyms, translations, definition, scope, sub- and superclasses. This domain-specific knowledge of a topic is exploited by the hyperCIS IRS to automatically generate search queries. These queries are passed to a text search engine, which determines adequate documents from different configurable categories with customizable contents. The IRS was integrated into the hyperCIS hospital information system and allows the fast and comfortable access to relevant documents fitting to the demands of the current task.