Conferences on applied research require more complicated taxonomy than traditional organization of conferences by tracks. A topic of a paper, submitted to a conference on the applied research and the keywords, outlined by authors can be discussed in more than one proposed conference track. Sorting out the papers submitted to a scientific conference in the proposed categories and tracks is becoming a nontrivial task. Conference organizing committees try to schedule submitted papers very carefully to increase the success rate of the conference. For example, the organizers of The Hawaii International Conference on System Science 2001(HICSS-34) allocated the theme similarities in papers that were submitted into different tracks and identified 6 cross-track themes to schedule them appropriately.In this paper, we offer a prototype matching system for text retrieval by content and try it out on the HICSS 34 conference proceeding. On the one hand, the system assists the conference organizers to automatically establish semantic similarities among papers and allocate them into common themes. On the other hand, the system assists the attendees to retrieve the papers from the conference proceedings based on their content similarities. A user can take an abstract or a paragraph from an interesting paper, and use it as a prototype query. The information system is based on document preprocessing, "smart" document encoding and prototype-matching clustering of a text collection.