At the cost of result quality, one could exploit social networks as a possible solution: promote the pages that your neighbors visit for an extended period of time (and thus deem to be of high value) by a factor corresponding to said neighbor's distance from you. If the queries are slightly randomized such that their order differs per person and per session, then new possible results could tested.

If you're using a 24 hour clock, then there should be ~365 of those events per year (can only have one per day by definition, every day has a corresponding day/month to hour:minute pair) -- since we're looking at events that can occur on a minutely basis, that means (days in year)/(minutes in year) so wolfram alpha says 1/1440.

Two provisos: first, it's really late so there's probably something wrong with the math up there; second, that wouldn't count other significant patterns (like, 01/02 03:04 or something) because that's kinda difficult to quantify.