I got a link to this paper by Ira Cohen, Co-Founder and Chief Scientist of Anodot. The paper full title is:Roberto J. Bayardo, Yiming Ma, and Ramakrishnan Srikant. 2007. Scaling up all pairs similarity search. In Proceedings of the 16th international conference on World Wide Web (WWW '07). ACM, New York, NY, USA, 131-140.
It seems like a simple method which works well when the compared pairs of vectors are sparse. It is also accompanied by open source code.