As a type of relevance feedback, Scatter/Gather demonstrates an interactive approach to relevance mapping and reinforcement. The Scatter/Gather model, proposed by Cutting, Karger, Pedersen, and Tukey (1992), is well known for its effectiveness in situations where it is difficult to precisely specify a query. However, online clustering on a large data corpus is computationally complex and extremely time consuming. This has prohibited the method's real world application for responsive services. In this paper, we proposed and evaluated a new clustering algorithm called LAIR2, which has linear worst-case time complexity and constant running time average for Scatter/Gather browsing. Our experiment showed when running on a single processor, the LAIR2 online clustering algorithm is several hundred times faster than a classic parallel algorithm running on multiple processors. The efficiency of the LAIR2 algorithm promises real-time Scatter/Gather browsing services. We have implemented an online visualization prototype, namely, LAIR2 Scatter/Gather browser, to demonstrate its utility and usability.